1. Computers
  2. Display Drivers
  3. Graphics Cards
  4. Memory
  5. Motherboards
  6. Processors
  7. Software
  8. Storage
  9. Operating Systems


Facebook RSS Twitter Twitter Google Plus


Phoronix Test Suite

OpenBenchmarking Benchmarking Platform
Phoromatic Test Orchestration

Zack Rusin Talks About Gallium3D's TGSI IR

Mesa

Published on 28 October 2010 06:41 PM EDT
Written by Michael Larabel in Mesa
2 Comments

Lately there's been a lot of talk about Gallium3D's IR known as TGSI, or Tokenized Gallium Shader Instructions, and attempts by some to replace this intermediate representation. Efforts toward improving TGSI are not particularly new, but it's been going on for a while and then just earlier this month a new shader and compiler stack was proposed by LunarG. As part of the LunarGLASS proposal, the LLVM IR would be used as a replacement to TGSI.

Zack Rusin of VMware (formerly with Tungsten Graphics) has just written a blog post about Gallium3D's Tokenized Gallium Shader Instructions for those interested in more information regarding the technical side of the IR and its current shortcomings and hurdles being experienced by these open-source GPU driver developers.

Zack's blog post about the IR can be read on his Blogger page. As some takeaway comments for those not interested in all of the technical details but just an overview of the situation, "[Tungsten Graphics'] lofty goal of making the IR so much easier and quicker to adopt took a pretty severe beating. It's especially disappointing since if you look at some of the documentation e.g. for AMD Intermediate Language you'll notice that this stuff is essentially Direct3D assembly which is essentially TGSI (and most of the parts that are in AMD IL and not in TGSI are parts that will be added to TGSI) . So they have this code. In the case of AMD it's even sadder because the crucial code that we need for OpenCL right now is OpenCL C -> TGSI LLVM backend which AMD already does for their IL. Some poor schmuck will have to sit down and write more/less the same code."

The most important paragraph in Zack's blog post is perhaps, "So we're left with Free Software developers who don't have access to the Direct3D functional spec and who are being confused by the IR which is unlike anything they've seen (pre-declared registers, typeless...) which on top of it is not easily transformable. TGSI is very readable, simple and pretty easy to debug though so it's not all negative. It's also great if you never have to optimize or transform its structure which unfortunately is rather rare. If we abandon the hope of having the code from Windows drivers injected in the GNU/Linux drivers it becomes pretty clear that we could do better than TGSI. Personally I just abhor the idea of rolling out our own IR. IR in the true sense of that word. Crazy as it may sound I'd really like my compiler stuff to be written by compiler experts. It's the main reason why I really like the idea of using LLVM IR as our IR."

About The Author
Michael Larabel is the principal author of Phoronix.com and founded the web-site in 2004 with a focus on enriching the Linux hardware experience and being the largest web-site devoted to Linux hardware reviews, particularly for products relevant to Linux gamers and enthusiasts but also commonly reviewing servers/workstations and embedded Linux devices. Michael has written more than 10,000 articles covering the state of Linux hardware support, Linux performance, graphics hardware drivers, and other topics. Michael is also the lead developer of the Phoronix Test Suite, Phoromatic, and OpenBenchmarking.org automated testing software. He can be followed via and or contacted via .
Latest Articles & Reviews
  1. Sub-$20 802.11n USB WiFi Adapter That's Linux Friendly
  2. The Lenovo T450s Is Working Beautifully With Linux
  3. Linux 4.0 SSD EXT4 / Btrfs / XFS / F2FS Benchmarks
  4. Linux 4.0 Hard Drive Comparison With Six File-Systems
  5. Lenovo ThinkPad T450s Broadwell Preview
  6. How Open-Source Allowed Valve To Implement VULKAN Much Faster On The Source 2 Engine
Latest Linux News
  1. AMD Open-Sources "Addrlib" From Catalyst
  2. AMD Releases New "AMDGPU" Linux Kernel Driver & Mesa Support
  3. A Gigabyte Sandy/Ivy Bridge Motherboard Now Handled By Coreboot
  4. Linux 3.16 Through Linux 4.0 Performance Benchmarks
  5. Intel's Windows Driver Now Supports OpenGL 4.4, Linux Driver Still With OpenGL 3.3
  6. DRM Graphics Updates Sent In For The Linux 4.1 Kernel
  7. More eBPF Improvements Heading To Linux 4.1
  8. LLDB Is Getting Into Shape For Linux 64-bit Debugging
  9. Wine-Staging 1.7.41 Works On Improved Debugging Support
  10. GNOME 3.18 Release Schedule: 23 September Release
Most Viewed News This Week
  1. Nouveau: NVIDIA's New Hardware Is "VERY Open-Source Unfriendly"
  2. LibreOffice 4.5 Bumped To Become LibreOffice 5.0
  3. Linux Audio Is Being Further Modernized With The 4.1 Kernel
  4. KDBUS Is Taking A Lot Of Heat, Might Be Delayed From Mainline Linux Kernel
  5. VirtualBox 5.0 Beta 2 Released
  6. ZFS & Libdvdcss Should Soon Be In Debian
  7. Ubuntu 15.04 Now Under Final Freeze
  8. EXT4 In Linux 4.1 Adds File-System Level Encryption